use autocrop instead of facexlib #26

New Issue

claunia · 2026-01-29T21:37:58Z

claunia commented

2026-01-29 21:37:58 +00:00

Originally created by @AK391 on GitHub (Jul 15, 2021).

https://github.com/leblancfg/autocrop autcrop does not require extra steps in installation as facexlib does

Originally created by @AK391 on GitHub (Jul 15, 2021). https://github.com/leblancfg/autocrop autcrop does not require extra steps in installation as facexlib does

claunia closed this issue

2026-01-29 21:37:58 +00:00

claunia commented

2026-01-29 21:37:59 +00:00

@woctezuma commented on GitHub (Jul 15, 2021):

First, FaceXLib is developed by the first author of GFP-GAN.

Second, Autocrop is a wrapper around the Cascade Classifier of OpenCV, which was published [1] in 2004.
In contrast, the face detection in FaceXLib is based on RetinaFace, which was published [2] in 2019, so much more recent.

[1] Viola, Paul, and Michael J. Jones. "Robust real-time face detection." International journal of computer vision 57.2 (2004): 137-154.

[2] Deng, Jiankang, et al. "Retinaface: Single-stage dense face localisation in the wild." arXiv preprint arXiv:1905.00641 (2019).

@woctezuma commented on GitHub (Jul 15, 2021): First, [FaceXLib](https://github.com/xinntao/facexlib) is developed by **the first author** of GFP-GAN. Second, Autocrop is a wrapper around [the Cascade Classifier](https://docs.opencv.org/master/db/d28/tutorial_cascade_classifier.html) of OpenCV, which was published [1] **in 2004**. In contrast, the face detection in FaceXLib is based on [RetinaFace](https://github.com/biubug6/Pytorch_Retinaface), which was published [2] **in 2019**, so much more recent. [1] Viola, Paul, and Michael J. Jones. "Robust real-time face detection." International journal of computer vision 57.2 (2004): 137-154. [2] Deng, Jiankang, et al. "Retinaface: Single-stage dense face localisation in the wild." arXiv preprint arXiv:1905.00641 (2019).

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: TencentARC/GFPGAN#26